Release 0.3 (#235)

.github/CONTRIBUTING.md

@@ -26,6 +26,17 @@ Take a look to the conventions established by existing code:
 * Every module should provide comprehensive tests at the end, in its `mod tests {}` sub-module. These tests can be flagged or not with configuration flags to allow WebAssembly target.
 * Run `cargo doc --no-deps --open` and read the generated documentation in the browser to be sure that your changes reflects in the documentation and new code is documented.
 
+#### digging deeper
+* a nice overview of the codebase is given by [static analyzer](https://mozilla.github.io/rust-code-analysis/metrics.html):
+```
+$ cargo install rust-code-analysis-cli
+// print metrics for every module
+$ rust-code-analysis-cli -m -O json -o . -p src/ --pr
+// print full AST for a module
+$ rust-code-analysis-cli -p src/algorithm/neighbour/fastpair.rs --ls 22 --le 213 -d > ast.txt
+```
+* find more information about what happens in your binary with [`twiggy`](https://rustwasm.github.io/twiggy/install.html). This need a compiled binary so create a brief `main {}` function using `smartcore` and then point `twiggy` to that file.
+
 ## Issue Report Process
 
 1. Go to the project's issues.

.github/DEVELOPERS.md

@@ -1,4 +1,7 @@
-# Smartcore: Introduction to modules
+# smartcore: Introduction to modules
+
+Important source of information:
+* [Rust API guidelines](https://rust-lang.github.io/api-guidelines/about.html)
 
 ## Walkthrough: traits system and basic structures
 

.gitignore

@@ -26,4 +26,6 @@ src.dot
 out.svg
 
 FlameGraph/
-out.stacks
+out.stacks
+*.json
+*.txt

CHANGELOG.md

@@ -4,22 +4,29 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [0.3.0] - 2022-11-09 
 
 ## Added
-- Seeds to multiple algorithims that depend on random number generation.
-- Added feature `js` to use WASM in browser
-- Drop `nalgebra-bindings` feature
-- Complete refactoring with *extensive API changes* that includes:
+- WARNING: Breaking changes!
+- Complete refactoring with **extensive API changes** that includes:
     * moving to a new traits system, less structs more traits
     * adapting all the modules to the new traits system
-    * moving towards Rust 2021, in particular the use of `dyn` and `as_ref`
-    * reorganization of the code base, trying to eliminate duplicates
+    * moving to Rust 2021, use of object-safe traits and `as_ref`
+    * reorganization of the code base, eliminate duplicates
+- implements `readers` (needs "serde" feature) for read/write CSV file, extendible to other formats
+- default feature is now Wasm-/Wasi-first
 
-## BREAKING CHANGE
-- Added a new parameter to `train_test_split` to define the seed.
+## Changed
+- WARNING: Breaking changes!
+- Seeds to multiple algorithims that depend on random number generation
+- Added a new parameter to `train_test_split` to define the seed
+- changed use of "serde" feature
+
+## Dropped
+- WARNING: Breaking changes!
+- Drop `nalgebra-bindings` feature, only `ndarray` as supported library
 
-## [0.2.1] - 2022-05-10
+## [0.2.1] - 2021-05-10
 
 ## Added
 - L2 regularization penalty to the Logistic Regression

Cargo.toml

@@ -1,16 +1,23 @@
 [package]
 name = "smartcore"
-description = "The most advanced machine learning library in rust."
+description = "Machine Learning in Rust."
 homepage = "https://smartcorelib.org"
-version = "0.4.0"
-authors = ["SmartCore Developers"]
+version = "0.3.0"
+authors = ["smartcore Developers"]
 edition = "2021"
 license = "Apache-2.0"
 documentation = "https://docs.rs/smartcore"
 repository = "https://github.com/smartcorelib/smartcore"
 readme = "README.md"
 keywords = ["machine-learning", "statistical", "ai", "optimization", "linear-algebra"]
 categories = ["science"]
+exclude = [
+    ".github",
+    ".gitignore",
+    "smartcore.iml",
+    "smartcore.svg",
+    "tests/"
+]
 
 [dependencies]
 approx = "0.5.1"
@@ -19,32 +26,31 @@ ndarray = { version = "0.15", optional = true }
 num-traits = "0.2.12"
 num = "0.4"
 rand = { version = "0.8.5", default-features = false, features = ["small_rng"] }
+getrandom = "*"
 rand_distr = { version = "0.4", optional = true }
 serde = { version = "1", features = ["derive"], optional = true }
 
 [features]
-default = ["serde", "datasets"]
+default = []
 serde = ["dep:serde"]
 ndarray-bindings = ["dep:ndarray"]
-datasets = ["dep:rand_distr", "std"]
-std = ["rand/std_rng", "rand/std"]
-# wasm32 only
+datasets = ["dep:rand_distr", "std_rand", "serde"]
+std_rand = ["rand/std_rng", "rand/std"]
+# used by wasm32-unknown-unknown for in-browser usage
 js = ["getrandom/js"]
 
 [target.'cfg(target_arch = "wasm32")'.dependencies]
 getrandom = { version = "0.2", optional = true }
 
+[target.'cfg(all(target_arch = "wasm32", not(target_os = "wasi")))'.dev-dependencies]
+wasm-bindgen-test = "0.3"
+
 [dev-dependencies]
 itertools = "*"
-criterion = { version = "0.4", default-features = false }
 serde_json = "1.0"
 bincode = "1.3.1"
 
-[target.'cfg(all(target_arch = "wasm32", not(target_os = "wasi")))'.dev-dependencies]
-wasm-bindgen-test = "0.3"
-
 [workspace]
-resolver = "2"
 
 [profile.test]
 debug = 1

LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 2019-present at SmartCore developers (smartcorelib.org) 
+   Copyright 2019-present at smartcore developers (smartcorelib.org) 
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

README.md

@@ -1,6 +1,6 @@
 <p align="center">
   <a href="https://smartcorelib.org">
-    <img src="smartcore.svg" width="450" alt="SmartCore">    
+    <img src="smartcore.svg" width="450" alt="smartcore">    
   </a>  
 </p>
 <p align = "center">
@@ -18,4 +18,4 @@
 -----
 [![CI](https://github.com/smartcorelib/smartcore/actions/workflows/ci.yml/badge.svg)](https://github.com/smartcorelib/smartcore/actions/workflows/ci.yml)
 
-To start getting familiar with the new Smartcore v0.5 API, there is now available a [**Jupyter Notebook environment repository**](https://github.com/smartcorelib/smartcore-jupyter). Please see instructions there, contributions welcome see [CONTRIBUTING](.github/CONTRIBUTING.md).
+To start getting familiar with the new smartcore v0.5 API, there is now available a [**Jupyter Notebook environment repository**](https://github.com/smartcorelib/smartcore-jupyter). Please see instructions there, contributions welcome see [CONTRIBUTING](.github/CONTRIBUTING.md).

src/algorithm/neighbour/cover_tree.rs

@@ -64,7 +64,7 @@ struct Node {
     max_dist: f64,
     parent_dist: f64,
     children: Vec<Node>,
-    scale: i64,
+    _scale: i64,
 }
 
 #[derive(Debug)]
@@ -84,7 +84,7 @@ impl<T: Debug + PartialEq, D: Distance<T>> CoverTree<T, D> {
             max_dist: 0f64,
             parent_dist: 0f64,
             children: Vec::new(),
-            scale: 0,
+            _scale: 0,
         };
         let mut tree = CoverTree {
             base,
@@ -245,7 +245,7 @@ impl<T: Debug + PartialEq, D: Distance<T>> CoverTree<T, D> {
             max_dist: 0f64,
             parent_dist: 0f64,
             children: Vec::new(),
-            scale: 100,
+            _scale: 100,
         }
     }
 
@@ -306,7 +306,7 @@ impl<T: Debug + PartialEq, D: Distance<T>> CoverTree<T, D> {
                     max_dist: 0f64,
                     parent_dist: 0f64,
                     children,
-                    scale: 100,
+                    _scale: 100,
                 }
             } else {
                 let mut far: Vec<DistanceSet> = Vec::new();
@@ -375,7 +375,7 @@ impl<T: Debug + PartialEq, D: Distance<T>> CoverTree<T, D> {
                         max_dist: self.max(consumed_set),
                         parent_dist: 0f64,
                         children,
-                        scale: (top_scale - max_scale),
+                        _scale: (top_scale - max_scale),
                     }
                 }
             }

src/cluster/kmeans.rs

@@ -11,7 +11,7 @@
 //! these re-calculated centroids becoming the new centers of their respective clusters. Next all instances of the training set are re-assigned to their closest cluster again.
 //! This iterative process continues until convergence is achieved and the clusters are considered settled.
 //!
-//! Initial choice of K data points is very important and has big effect on performance of the algorithm. SmartCore uses k-means++ algorithm to initialize cluster centers.
+//! Initial choice of K data points is very important and has big effect on performance of the algorithm. `smartcore` uses k-means++ algorithm to initialize cluster centers.
 //!
 //! Example:
 //!
@@ -74,7 +74,7 @@ pub struct KMeans<TX: Number, TY: Number, X: Array2<TX>, Y: Array1<TY>> {
     k: usize,
     _y: Vec<usize>,
     size: Vec<usize>,
-    distortion: f64,
+    _distortion: f64,
     centroids: Vec<Vec<f64>>,
     _phantom_tx: PhantomData<TX>,
     _phantom_ty: PhantomData<TY>,
@@ -313,7 +313,7 @@ impl<TX: Number, TY: Number, X: Array2<TX>, Y: Array1<TY>> KMeans<TX, TY, X, Y>
             k: parameters.k,
             _y: y,
             size,
-            distortion,
+            _distortion: distortion,
             centroids,
             _phantom_tx: PhantomData,
             _phantom_ty: PhantomData,
@@ -470,7 +470,7 @@ mod tests {
         wasm_bindgen_test::wasm_bindgen_test
     )]
     #[test]
-    fn fit_predict_iris() {
+    fn fit_predict() {
         let x = DenseMatrix::from_2d_array(&[
             &[5.1, 3.5, 1.4, 0.2],
             &[4.9, 3.0, 1.4, 0.2],

src/dataset/mod.rs

@@ -1,6 +1,6 @@
 //! Datasets
 //!
-//! In this module you will find small datasets that are used in SmartCore mostly for demonstration purposes.
+//! In this module you will find small datasets that are used in `smartcore` mostly for demonstration purposes.
 pub mod boston;
 pub mod breast_cancer;
 pub mod diabetes;

src/ensemble/mod.rs

@@ -7,7 +7,7 @@
 //! set and then aggregate their individual predictions to form a final prediction. In classification setting the overall prediction is the most commonly
 //! occurring majority class among the individual predictions.
 //!
-//! In SmartCore you will find implementation of RandomForest - a popular averaging algorithms based on randomized [decision trees](../tree/index.html).
+//! In `smartcore` you will find implementation of RandomForest - a popular averaging algorithms based on randomized [decision trees](../tree/index.html).
 //! Random forests provide an improvement over bagged trees by way of a small tweak that decorrelates the trees. As in bagging, we build a number of
 //! decision trees on bootstrapped training samples. But when building these decision trees, each time a split in a tree is considered,
 //! a random sample of _m_ predictors is chosen as split candidates from the full set of _p_ predictors.

src/ensemble/random_forest_classifier.rs

@@ -104,7 +104,6 @@ pub struct RandomForestClassifier<
     X: Array2<TX>,
     Y: Array1<TY>,
 > {
-    parameters: Option<RandomForestClassifierParameters>,
     trees: Option<Vec<DecisionTreeClassifier<TX, TY, X, Y>>>,
     classes: Option<Vec<TY>>,
     samples: Option<Vec<Vec<bool>>>,
@@ -198,7 +197,6 @@ impl<TX: Number + FloatNumber + PartialOrd, TY: Number + Ord, X: Array2<TX>, Y:
 {
     fn new() -> Self {
         Self {
-            parameters: Option::None,
             trees: Option::None,
             classes: Option::None,
             samples: Option::None,
@@ -501,7 +499,6 @@ impl<TX: FloatNumber + PartialOrd, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY
         }
 
         Ok(RandomForestClassifier {
-            parameters: Some(parameters),
             trees: Some(trees),
             classes: Some(classes),
             samples: maybe_all_samples,
@@ -637,7 +634,7 @@ mod tests {
         wasm_bindgen_test::wasm_bindgen_test
     )]
     #[test]
-    fn fit_predict_iris() {
+    fn fit_predict() {
         let x = DenseMatrix::from_2d_array(&[
             &[5.1, 3.5, 1.4, 0.2],
             &[4.9, 3.0, 1.4, 0.2],

src/ensemble/random_forest_regressor.rs

@@ -98,7 +98,6 @@ pub struct RandomForestRegressor<
     X: Array2<TX>,
     Y: Array1<TY>,
 > {
-    parameters: Option<RandomForestRegressorParameters>,
     trees: Option<Vec<DecisionTreeRegressor<TX, TY, X, Y>>>,
     samples: Option<Vec<Vec<bool>>>,
 }
@@ -177,7 +176,6 @@ impl<TX: Number + FloatNumber + PartialOrd, TY: Number, X: Array2<TX>, Y: Array1
 {
     fn new() -> Self {
         Self {
-            parameters: Option::None,
             trees: Option::None,
             samples: Option::None,
         }
@@ -434,7 +432,6 @@ impl<TX: Number + FloatNumber + PartialOrd, TY: Number, X: Array2<TX>, Y: Array1
         }
 
         Ok(RandomForestRegressor {
-            parameters: Some(parameters),
             trees: Some(trees),
             samples: maybe_all_samples,
         })